English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

The attention mechanism has demonstrated superior performance for inferenceover nodes in graph neural networks (GNNs), however, they result in a highcomputational burden during both training and inference. We propose FastGAT, amethod to make attention based GNNs lightweight by using spectralsparsification to generate an optimal pruning of the input graph. This resultsin a per-epoch time that is almost linear in the number of graph nodes asopposed to quadratic. We theoretically prove that spectral sparsificationpreserves the features computed by the GAT model, thereby justifying ouralgorithm. We experimentally evaluate FastGAT on several large real world graphdatasets for node classification tasks under both inductive and transductivesettings. FastGAT can dramatically reduce (up to \textbf{10x}) thecomputational time and memory requirements, allowing the usage of attentionbased GNNs on large graphs.

Fast Graph Attention Networks Using Effective Resistance Based Graph Sparsification